Self-adaptive constructivism in Neural XCS and XCSF

For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility guided by the environment at any given time. This paper presents the use of constructivism-inspired mechanisms within a neural learning classifier system which exploits parameter self-adaptation as an approach to realize such behaviour. The system uses a rule structure in which each is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the system. Further, the use of computed predictions is shown possible.

[1]  Martin V. Butz,et al.  An algorithmic description of XCS , 2000, Soft Comput..

[2]  Daniele Loiacono,et al.  Classifier systems that compute action mappings , 2007, GECCO '07.

[3]  G. Edelman.  Neural Darwinism: The Theory Of Neuronal Group Selection , 1989 .

[4]  H. Ishibuchi.  Genetic fuzzy systems: evolutionary tuning and learning of fuzzy knowledge bases , 2004 .

[5]  Stewart W. Wilson.  Function approximation with a classifier system , 2001 .

[6]  Larry Bull,et al.  A Genetic Programming-based Classifier System , 1999, GECCO.

[7]  Larry Bull,et al.  A Neural Learning Classifier System with Self-Adaptive Constructivism for Mobile Robot Control , 2006, Artificial Life.

[8]  Pier Luca Lanzi,et al.  An Analysis of Generalization in the XCS Classifier System , 1999, Evolutionary Computation.

[9]  Tim Kovacs,et al.  Learning Classifier Systems, International Workshops, IWLCS 2003-2005, Revised Selected Papers , 2007, IWLCS.

[10]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[11]  H. Crichton-Miller.  Adaptation , 1926 .

[12]  James L. McClelland.  Parallel Distributed Processing , 2005 .

[13]  Larry Bull,et al.  Using the XCS Classifier System for Multi-objective Reinforcement Learning Problems , 2007, Artificial Life.

[14]  Inman Harvey,et al.  Seeing the Light: Artiicial Evolution, Real Vision Seeing the Light: Artiicial Evolution, Real Vision , 1994 .

[15]  Stewart W. Wilson.  Three Architectures for Continuous Action , 2005, IWLCS.

[16]  Zbigniew Michalewicz,et al.  Evolutionary Computation 2 , 2000 .

[17]  Larry Bull,et al.  Accuracy-based Neuro And Neuro-fuzzy Classifier Systems , 2002, GECCO.

[18]  Francisco Herrera,et al.  Other Genetic Fuzzy Rule-Based System Paradigms , 2001 .

[19]  Tim Kovacs,et al.  Advances in Learning Classifier Systems , 2001, Lecture Notes in Computer Science.

[20]  Larry Bull,et al.  Self-adaptive mutation in classifier system controllers , 2000 .

[21]  Hans-Paul Schwefel,et al.  Numerical Optimization of Computer Models , 1982 .

[22]  T. Sejnowski,et al.  Irresistible environment meets immovable neurons , 1997, Behavioral and Brain Sciences.

[23]  Stewart W. Wilson.  Classifier Fitness Based on Accuracy , 1995, Evolutionary Computation.

[24]  Mark H. Johnson.  The neural basis of cognitive development. , 1998 .

[25]  Juan Julián Merelo Guervós,et al.  Parallel Problem Solving from Nature — PPSN VII , 2002, Lecture Notes in Computer Science.

[26]  Larry Bull,et al.  On Using Constructivism in Neural Classifier Systems , 2002, PPSN.

[27]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[28]  Stewart W. Wilson.  ZCS: A Zeroth Level Classifier System , 1994, Evolutionary Computation.